Mistral AI

Mistral AI: Devstral Medium

mistralai/devstral-medium-2507

Access Devstral Medium from Mistral AI using Puter.js AI API.

Get Started
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';

puter.ai.chat("Explain quantum computing in simple terms", {
    model: "mistralai/devstral-medium-2507"
}).then(response => {
    document.body.innerHTML = response.message.content;
});
<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.chat("Explain quantum computing in simple terms", {
            model: "mistralai/devstral-medium-2507"
        }).then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>
# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://api.puter.com/puterai/openai/v1/",
    api_key="YOUR_PUTER_AUTH_TOKEN",
)

response = client.chat.completions.create(
    model="mistralai/devstral-medium-2507",
    messages=[
        {"role": "user", "content": "Explain quantum computing in simple terms"}
    ],
)

print(response.choices[0].message.content)
curl https://api.puter.com/puterai/openai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_PUTER_AUTH_TOKEN" \
  -d '{
    "model": "mistralai/devstral-medium-2507",
    "messages": [
      {"role": "user", "content": "Explain quantum computing in simple terms"}
    ]
  }'

Model Card

Devstral Medium is a high-performance agentic coding model achieving 61.6% on SWE-Bench Verified. It excels at complex software engineering tasks across entire codebases, surpassing GPT-4.1 and Gemini 2.5 Pro in code-related tasks at a fraction of the cost.

Context Window 131K

tokens

Max Output 131K

tokens

Input Cost $0.4

per million tokens

Output Cost $2

per million tokens

Input text

modalities

Tool Use Yes

 

Knowledge Cutoff May 2025

 

Release Date Jul 10, 2025

 

Output Speed 142

tokens / sec

Latency 0.47s

time to first token

Model Playground

Try Devstral Medium instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.

Chat mistralai/devstral-medium-2507
Mistral AI
Chat with Devstral Medium
Powered by Puter.js

Benchmarks

How Devstral Medium performs on standard evaluations.

Artificial Analysis
Intelligence Index
18.7
Better than 51% of tracked models
Artificial Analysis
Coding Index
15.9
Better than 45% of tracked models
Artificial Analysis
Math Index
4.7
Better than 7% of tracked models
BenchmarkScore
GPQA Diamond Graduate-level science Q&A
49.2%
Humanity's Last Exam Cross-domain reasoning
3.8%
LiveCodeBench Recent coding problems
33.7%
SciCode Scientific programming
29.4%
MATH-500 Competition math
70.7%
AIME 2024 Advanced math exam
6.7%
AIME 2025 Advanced math exam
4.7%
IFBench Instruction following
29.9%
LCR Long-context reasoning
28.7%
Terminal-Bench Hard Agentic terminal tasks
9.1%
τ²-Bench Tool use / agents
19.9%

Scores sourced from Artificial Analysis.

Frequently Asked Questions

How do I use Devstral Medium?

You can access Devstral Medium by Mistral AI through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.

Is Devstral Medium free?

Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Devstral Medium to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.

What is the pricing for Devstral Medium?
Pricing for Devstral Medium is based on the number of input and output tokens used per request.
Price per 1M tokens
Input$0.4
Output$2
Who created Devstral Medium?

Devstral Medium was created by Mistral AI and released on Jul 10, 2025.

What is the context window of Devstral Medium?

Devstral Medium supports a context window of 131K tokens. For reference, that is roughly equivalent to 262 pages of text.

What is the max output length of Devstral Medium?

Devstral Medium can generate up to 131K tokens in a single response.

What is the knowledge cutoff of Devstral Medium?

Devstral Medium has a knowledge cutoff date of May 2025. This means the model was trained on data available up to that date.

What types of input can Devstral Medium process?

Devstral Medium accepts the following input types: text. It produces: text.

Does Devstral Medium support tool use (function calling)?

Yes, Devstral Medium supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.

Does it work with React / Vue / Vanilla JS / Node / etc.?

Yes — the Devstral Medium API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.

Get started with Puter.js

Add Devstral Medium to your app without worrying about API keys or setup.

Read the Docs View Tutorials